Application Google Earth Engine for monitoring green space changes in Thu Duc city using Sentinel-2 images during 2019–2024

Abstract

Urbanization has increased the extent of impervious surfaces, indirectly placing pressure on
the urban green ecosystem in Thu Duc City. This study utilizes Sentinel-2 satellite imagery from 2019
and 2024, combined with the Random Forest algorithm on the Google Earth Engine platform, to generate
green space maps of Thu Duc City and analyze changes during the study period. The results indicate a
declining trend in green space by 2024 compared to 2019, particularly in riverside areas and the eastern
part of the city. The integration of Machine Learning in satellite image classification has enhanced
accuracy, automated the processing of large datasets, and effectively supported green space monitoring
amid the growing challenges of urbanization and climate change.